© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 36-GEMMASCOPE-RES-16K
    11. 14962
    Prev
    Next
    INDEX
    Explanations

    references to bugs or issues in processes that require fixing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_36/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.36.hook_resid_post
    Hook Layer
    36
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    
    -0.49
     autorytatywna
    -0.44
    Derbyniad
    -0.43
    ensory
    -0.42
    orghe
    -0.41
    agu
    -0.38
    nEnter
    -0.37
    PSK
    -0.37
    richTextPanel
    -0.36
     degener
    -0.35
    POSITIVE LOGITS
     corrected
    2.08
     correcting
    2.06
     correction
    2.02
     rectify
    1.88
     remedy
    1.84
     corregir
    1.83
     corrects
    1.83
     remedied
    1.80
     corrective
    1.79
    corrected
    1.79
    Activations Density 0.973%

    No Known Activations